Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numeric expressions and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sapp
    -0.69
    76561
    -0.67
    atown
    -0.67
    £ı
    -0.66
     compr
    -0.64
    helps
    -0.63
    Joined
    -0.61
     Bounty
    -0.60
    lication
    -0.60
     Ran
    -0.59
    POSITIVE LOGITS
     billion
    1.23
     trillion
    1.22
    billion
    1.19
    %-
    1.04
     million
    1.03
     decades
    0.98
    century
    0.96
    percent
    0.94
     crore
    0.93
    million
    0.93
    Act Density 0.216%

    No Known Activations